Search Results for author:
Found 55 papers, 22 papers with code
Inference on Optimal Dynamic Policies via Softmax Approximation
Estimating optimal dynamic policies from offline data is a fundamental problem in dynamic decision making.
Post-Episodic Reinforcement Learning Inference
Our goal is to be able to evaluate counterfactual adaptive policies after data collection and to estimate structural parameters such as dynamic treatment effects, which can be used for credit assignment (e. g. what was the effect of the first period action on the final outcome).
Minimax Instrumental Variable Regression and $L_2$ Convergence Guarantees without Identification or Closedness
In this paper, we study nonparametric estimation of instrumental variable (IV) regressions.
Empirical Analysis of Model Selection for Heterogenous Causal Effect Estimation
Unlike model selection in machine learning, we cannot use the technique of cross-validation here as we do not observe the counterfactual potential outcome for any data point.
Synthetic Blip Effects: Generalizing Synthetic Controls for the Dynamic Treatment Regime
Our work avoids the combinatorial explosion in the number of units that would be required by a vanilla application of prior synthetic control and synthetic intervention methods in such dynamic treatment regime settings.
Partial Identification of Treatment Effects with Implicit Generative Models
We propose a new method for partial identification of average treatment effects(ATEs) in general causal graphs using implicit generative models comprising continuous and discrete random variables.
Inference on Strongly Identified Functionals of Weakly Identified Functions
In a variety of applications, including nonparametric instrumental variable (NPIV) analysis, proximal causal inference under unmeasured confounding, and missing-not-at-random data with shadow variables, we are interested in inference on a continuous linear functional (e. g., average causal effects) of nuisance function (e. g., NPIV regression) defined by conditional moment restrictions.
Debiased Machine Learning without Sample-Splitting for Stable Estimators
For instance, we show that the stability properties that we propose are satisfied for ensemble bagged estimators, built via sub-sampling without replacement, a popular technique in machine learning practice.
Towards efficient representation identification in supervised learning
In this work, we depart from these assumptions and ask: a) How can we get disentanglement when the auxiliary information does not provide conditional independence over the factors of variation?
Automatic Debiased Machine Learning for Dynamic Treatment Effects and General Nested Functionals
We extend the idea of automated debiased machine learning to the dynamic treatment regime and more generally to nested functionals.
Long Story Short: Omitted Variable Bias in Causal Machine Learning
Therefore, simple plausibility judgments on the maximum explanatory power of omitted variables (in explaining treatment and outcome variation) are sufficient to place overall bounds on the size of the bias.
Double/Debiased Machine Learning for Dynamic Treatment Effects
We consider the estimation of treatment effects in settings when multiple treatments are assigned over time and treatments can have a causal effect on future outcomes.
Asymptotics of the Bootstrap via Stability with Applications to Inference with Model Selection
One of the most commonly used methods for forming confidence intervals is the empirical bootstrap, which is especially expedient when the limiting distribution of the estimator is unknown.
RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests
We also propose a Random Forest method which learns a locally linear representation of the Riesz function.
Robust Generalized Method of Moments: A Finite Sample Viewpoint
For many inference problems in statistics and econometrics, the unknown parameter is identified by a set of moment conditions.
DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions
Estimation of causal effects involves crucial assumptions about the data-generating process, such as directionality of effect, presence of instrumental variables or mediators, and whether all relevant confounders are observed.
Incentivizing Compliance with Algorithmic Instruments
In rounds, a social planner interacts with a sequence of heterogeneous agents who arrive with their unobserved private type that determines both their prior preferences across the actions (e. g., control and treatment) and their baseline rewards without taking any treatment.
Knowledge Distillation as Semiparametric Inference
A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model.
Estimating the Long-Term Effects of Novel Treatments
Policy makers typically face the problem of wanting to estimate the long-term effects of novel treatments, while only having historical data of older treatment options.
Evidence-Based Policy Learning
The past years have seen seen the development and deployment of machine-learning algorithms to estimate personalized treatment-assignment policies from randomized controlled trials.
Adversarial Estimation of Riesz Representers
We provide an adversarial approach to estimating Riesz representers of linear functionals within arbitrary function spaces.
Asymptotics of the Empirical Bootstrap Method Beyond Asymptotic Normality
One of the most commonly used methods for forming confidence intervals for statistical inference is the empirical bootstrap, which is especially expedient when the limiting distribution of the estimator is unknown.
Bid Prediction in Repeated Auctions with Learning
We consider the problem of bid prediction in repeated auctions and evaluate the performance of econometric methods for learning agents using a dataset from a mainstream sponsored search auction marketplace.
Estimation and Inference with Trees and Forests in High Dimensions
We prove that if only $r$ of the $d$ features are relevant for the mean outcome function, then shallow trees built greedily via the CART empirical MSE criterion achieve MSE rates that depend only logarithmically on the ambient dimension $d$.
Minimax Estimation of Conditional Moment Models
We develop an approach for estimating models described via conditional moment restrictions, with a prototypical application being non-parametric instrumental variable regression.
Double/Debiased Machine Learning for Dynamic Treatment Effects via g-Estimation
We consider the estimation of treatment effects in settings when multiple treatments are assigned over time and treatments can have a causal effect on future outcomes or the state of the treated unit.
Dynamically Aggregating Diverse Information
An agent has access to multiple information sources, each of which provides information about a different attribute of an unknown state.
Semi-Parametric Efficient Policy Learning with Continuous Actions
Our results also apply if the model does not satisfy our semi-parametric form, but rather we measure regret in terms of the best projection of the true value function to this functional space.
Machine Learning Estimation of Heterogeneous Treatment Effects with Instruments
We develop a statistical learning approach to the estimation of heterogeneous effects, reducing the problem to the minimization of an appropriate loss function that depends on a set of auxiliary models (each corresponding to a separate prediction task).
Orthogonal Statistical Learning
We provide non-asymptotic excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target parameter depends on an unknown nuisance parameter that must be estimated from data.
Non-Parametric Inference Adaptive to Intrinsic Dimension
We show that if the intrinsic dimension of the covariate distribution is equal to $d$, then the finite sample estimation error of our estimator is of order $n^{-1/(d+2)}$ and our estimate is $n^{1/(d+2)}$-asymptotically normal, irrespective of $D$.
Regularized Orthogonal Machine Learning for Nonlinear Semiparametric Models
This paper proposes a Lasso-type estimator for a high-dimensional sparse parameter identified by a single index conditional moment restriction (CMR).
Orthogonal Random Forest for Causal Inference
We provide a consistency rate and establish asymptotic normality for our estimator.
Adversarial Generalized Method of Moments
We provide an approach for learning deep neural net representations of models described via conditional moment restrictions.
Expert identification of visual primitives used by CNNs during mammogram classification
This work interprets the internal representations of deep neural networks trained for classification of diseased tissue in 2D mammograms.
Semiparametric Contextual Bandits
This paper studies semiparametric contextual bandits, a generalization of the linear stochastic bandit problem where the reward for an action is modeled as a linear function of known action features confounded by an non-linear action-independent term.
Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing
We consider dynamic pricing with many products under an evolving but low-dimensional demand model.
Accurate Inference for Adaptive Linear Models
Estimators computed from adaptively collected data do not behave like their non-adaptive brethren.
Welfare Guarantees from Data
The notion of the price of anarchy takes a worst-case stance to efficiency analysis, considering instance independent guarantees of efficiency.
Learning to Bid Without Knowing your Value
We address online learning in complex auction settings, such as sponsored search auctions, where the value of the bidder is unknown to her, evolving in an arbitrary manner and observed only if the bidder wins an allocation.
Orthogonal Machine Learning: Power and Limitations
Double machine learning provides $\sqrt{n}$-consistent estimates of parameters of interest even when high-dimensional or nonparametric nuisance parameters are estimated at an $n^{-1/4}$ rate.
Training GANs with Optimism
Moreover, we show that optimistic mirror decent addresses the limit cycling problem in training WGANs.
Inference on Auctions with Weak Assumptions on Information
Given a sample of bids from independent auctions, this paper examines the question of inference on auction fundamentals (e. g. valuation distributions, welfare measures) under weak assumptions on information structure.
Robust Optimization for Non-Convex Objectives
We consider robust optimization problems, where the goal is to optimize in the worst case over a class of objective functions.
A Proof of Orthogonal Double Machine Learning with $Z$-Estimators
We consider two stage estimation with a non-parametric first stage and a generalized method of moments second stage, in a simpler setting than (Chernozhukov et al. 2016).
A Sample Complexity Measure with Applications to Learning Optimal Auctions
We introduce a new sample complexity measure, which we refer to as split-sample growth rate.
Optimal and Myopic Information Acquisition
We consider the problem of optimal dynamic information acquisition from many correlated information sources.
Oracle-Efficient Online Learning and Auction Design
We consider the design of computationally efficient online learning algorithms in an adversarial setting in which the learner has access to an offline optimization oracle.
The Price of Anarchy in Auctions
This survey outlines a general and modular theory for proving approximation guarantees for equilibria of auctions in complex settings.
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
We give an oracle-based algorithm for the adversarial contextual bandit problem, where either contexts are drawn i. i. d.
Bayesian Exploration: Incentivizing Exploration in Bayesian Games
As a key technical tool, we introduce the concept of explorable actions, the actions which some incentive-compatible policy can recommend with non-zero probability.
Efficient Algorithms for Adversarial Contextual Learning
We provide the first oracle efficient sublinear regret algorithms for adversarial versions of the contextual bandit problem.
Learning in Auctions: Regret is Hard, Envy is Easy
Our results for XOS valuations are enabled by a novel Follow-The-Perturbed-Leader algorithm for settings where the number of experts is infinite, and the payoff function of the learner is non-linear.
Fast Convergence of Regularized Learning in Games
We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equilibria in multiplayer normal form games.
No-Regret Learning in Bayesian Games
Recent price-of-anarchy analyses of games of complete information suggest that coarse correlated equilibria, which characterize outcomes resulting from no-regret learning dynamics, have near-optimal welfare.
